Claude-Red
About 80 offensive security skills for penetration testing, each focused on one attack surface.
Install
npx skills add SnailSploit/Claude-Red -a claude-code
npx skills add SnailSploit/Claude-Red -a claude-code -g
Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).
When to use
Use it on penetration tests and red-team engagements where you're authorized, to bring Claude up to speed on a specific attack surface quickly.
claude-red is a library of about 80 offensive security skills, each a SKILL.md file that gives Claude a methodology for one attack surface. Topics run from SQL injection to shellcode, and include Active Directory, API and JWT testing, OAuth, CI/CD pipelines and AI security. Skills load on demand from conversational triggers, so you don't pay context for the ones you aren't using.
The README lists authorized red teaming among its use cases and the skills are for security professionals. Use them only against systems you have written permission to test.
Related skills
-
rea
Lets your agent reverse engineer an app from the outside, down to native binaries, and then build its own version.
-
superpowers
A set of development habits for your agent: test first, debug systematically, and plan before you code.
-
skills
The skills Matt Pocock uses in his own day-to-day engineering work.
-
ECC
A ready-made setup for coding agents that adds skills, persistent memory and security checks.